A neural network model for constructing endophenotypes of common complex diseases: an application to male young-onset hypertension microarray data

Abstract

Motivation: Identification of disease-related genes using high-throughput microarray data is more difficult for complex diseases as compared with monogenic ones. We hypothesized that an endophenotype derived from transcriptional data is associated with a set of genes corresponding to a pathway cluster. We assumed that a complex disease is associated with multiple endophenotypes and can be induced by their up/downregulated gene expression patterns. Thus, a neural network model was adopted to simulate the gene–endophenotype–disease relationship in which endophenotypes were represented by hidden nodes.Results: We successfully constructed a three-endophenotype model for Taiwanese hypertensive males with high identification accuracy. Of the three endophenotypes, one is strongly protective, another is weakly protective and the third is highly correlated with developing young-onset male hypertension. Sixteen of the involved 101 genes were highly and consistently influential to the endophenotypes. Identification of SLC4A5, SLC5A10 and LDOC1 indicated that sodium/bicarbonate transport, sodium/glucose transport and cell-proliferation regulation may play important upstream roles and identification of BNIP1, APOBEC3F and LDOC1 suggested that apoptosis, innate immune response and cell-proliferation regulation may play important downstream roles in hypertension. The involved genes not only provide insights into the mechanism of hypertension but should also be considered in future gene mapping endeavors.Availability: Microarray data and test program are available at http://ms.iis.sinica.edu.tw/microarray/index.htmContact: pan@ibms.sinica.edu.tw or hsu@iis.sinica.edu.twSupplementary information: Supplementary data are available at Bioinformatics online.

The Renal Sodium Bicarbonate Cotransporter NBCe2: Is It a Major Contributor to Sodium and pH Homeostasis?

“…The association of these SNPs with salt sensitivity was replicated in the HyperPATH Cohort at Harvard with a meta-analysis demonstrating significant associations of both SNPs with salt sensitivity (rs7571842 ( P = 1.2×10 −5 ); rs1017783 ( P =1.1× 10 −4 )) [43••]. Our results [43••] are consistent with the association ofrs1017783 and increased blood pressure in African-Americans, Mexican-Americans, Euro-Americans, and Taiwanese [42••, 44••, 45••, 46, 47, 63••, 64]. Another SLC4A5 SNP (rs 10022637) ( P =2.07×10 −6 ) was found to be associated with salt sensitivity in a large cohort of Han Chinese; SLC4A5 rs1017783 was not genotyped [65].…”

“…Thus, we have demonstrated a functional link between SLC4A5 polymorphisms and renal sodium transport that could make contributions to salt sensitivity [11••]. As previously mentioned, studies from various investigators including ourselves have demonstrated a genetic link between NBCe2 polymorphisms and hypertension [11••, 42••, 43••, 44••, 45••, 46, 47, 63••, 64, 65]. However, these polymorphisms are not in the coding region for SLC4A5 (NBCe2).…”

The Divergence, Actions, Roles, and Relatives of Sodium-Coupled Bicarbonate Transporters

“…Genetic analysis links single nucleotide polymorphisms (SNPs) in the SLC4A5 gene locus with hypertension and other blood pressure-related traits (61,404,619,915,953,954), including peripheral artery disease (472). One study reports that the contribution of a particular SLC4A5 SNP to elevated systolic blood pressure in African-American women is greater in individuals with dark versus medium skin color (955).…”

Construction of gene clusters resembling genetic causal mechanisms for common complex disease with an application to young-onset hypertension

“…For very complex diseases, such as hypertension, GWAS have revealed very few genes despite a large number of patients that have been studied. It is generally accepted that common complex disease etiologies are heterogeneous in nature [5-8]. In “state of art” GWAS approach, however, inheritance models involving gene-gene interactions and gene-environment interactions [9-13] have not been taken into consideration.…”